MCP server
A program that exposes a set of tools and data to an AI assistant over the Model Context Protocol.
In detail.
A server declares what it can do at connection time, then waits. It holds the credentials for whatever it fronts, translates a tool call into an API request, and returns a result the model can read. In advertising, one server usually fronts one platform: its API version, its authentication, its rate limits, its error vocabulary.
Servers come in two shapes. A local server runs on the user's own machine and speaks over standard input and output. A remote server runs on someone else's infrastructure and is reached over HTTP, which is what makes hosted products possible.
Through an agent.
What changes when a model asks instead of a person.
The number of tools a server announces is the number of tool descriptions the model carries in its context for the whole conversation. A server announcing four hundred tools spends a large slice of the window before the first question is asked, which is why some servers announce a small core and expose the rest through a search tool.